metadata
base_model: ''
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: wav2GPT2MusiNewStricD3E5
results: []
wav2GPT2MusiNewStricD3E5
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2775
- Rouge1: 37.5957
- Rouge2: 10.8859
- Rougel: 29.7559
- Rougelsum: 29.7904
- Gen Len: 33.19
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.1175 | 1.0 | 983 | 2.5054 | 36.6389 | 9.7932 | 28.7186 | 28.771 | 30.04 |
| 2.6547 | 2.0 | 1966 | 2.3880 | 36.5342 | 10.597 | 29.092 | 29.0762 | 28.1 |
| 2.5787 | 3.0 | 2949 | 2.3239 | 37.5926 | 10.5376 | 29.0149 | 29.0558 | 34.72 |
| 2.5014 | 4.0 | 3932 | 2.2907 | 36.1982 | 9.8055 | 29.3162 | 29.3555 | 33.97 |
| 2.4805 | 5.0 | 4915 | 2.2775 | 37.5957 | 10.8859 | 29.7559 | 29.7904 | 33.19 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.2
- Tokenizers 0.13.3